Multi-perspective scaling convolutional neural networks for high-resolution MRI brain image segmentation

Abstract The occurrence of defect over the soft tissues and nervous system is gradually increasing where Magnetic Resonance Imaging (MRI) is the most preferred method for performing the examination. The brain tumor MR image segmentation performs functionalities like image reconstruction of affected (diseased tissues) and qualitative analysis of infected and normal tissues. The image segmentation accuracy with the physician’s perspective relies over the shape, size, and location of lesions tissues, appropriate diagnostic strategies, and disease determination. The outcomes of this investigation rely over Multi-Perspective Scaling Convolutional Neural Networks (MPS-CNN) model for segmenting brain tumors more effectually and accurately. The multi-scale inputs are given to the proposed CNN model to overcome the necessity to select the appropriate input scale based on the tumor size, neighborhood tumor analysis based on scaled images, and adoption towards various tumor sizes. Therefore, the segmentation accuracy can be increased based on the input multi-scale brain tumor images. Also, the faster segmentation with multi-scaling process accelerates the speed of ensuring real-time segmentation process. This scaling process can effectively segment the brain images in the MRI which enhances the generalization process. It is utilized for predicting the brain lesion tissue of MRI. The simulation is carried out in MATLAB environment. The anticipated MPS-CNN is compared with prevailing approaches like CNN, FCN, U-Net, SegNet, Deep V3, and Deep FCN. And the MPS-CNN shows better trade-off in contrary to other approaches.